nsl.configs.DecayConfig

Contains configuration for decaying a value during training.

nsl.configs.DecayConfig(
    decay_steps,
    decay_rate=attr_dict['decay_rate'].default,
    min_value=attr_dict['min_value'].default,
    decay_type=nsl.configs.DecayType.EXPONENTIAL_DECAY
)

decay_steps A scalar int32 or int64 Tensor or a Python number that specifies the decay frequency, specied in units of training steps. Must be positive.
decay_rate A scalar float32 or float64 Tensor or a Python number. Defaults to 0.96.
min_value minimal acceptable value after applying decay. Defaults to 0.0.
decay_type Type of decay function to apply. Defaults to nsl.configs.DecayType.EXPONENTIAL_DECAY.

Methods

__eq__

__eq__(
    other
)

Method generated by attrs for class DecayConfig.

__ge__

__ge__(
    other
)

Method generated by attrs for class DecayConfig.

__gt__

__gt__(
    other
)

Method generated by attrs for class DecayConfig.

__le__

__le__(
    other
)

Method generated by attrs for class DecayConfig.

__lt__

__lt__(
    other
)

Method generated by attrs for class DecayConfig.

__ne__

__ne__(
    other
)

Method generated by attrs for class DecayConfig.